Yonglong Tian

papers

11,990

total citations

papers (17)

StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners

NEURIPS 2023arXiv

210

citations

Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens

ICLR 2025arXiv

119

citations

Divide and Contrast: Self-Supervised Learning From Uncurated Data

ICCV 2021arXiv

110

citations

Scaling Laws of Synthetic Images for Model Training ... for Now

CVPR 2024arXiv

108

citations

Restart Sampling for Improving Generative Processes

NEURIPS 2023arXiv

citations

Learning Vision from Models Rivals Learning Vision from Data

CVPR 2024arXiv

citations

Co-Advise: Cross Inductive Bias Distillation

CVPR 2022arXiv

citations

Vision-Language Models Do Not Understand Negation

CVPR 2025arXiv

citations

Denoising Vision Transformers

ECCV 2024arXiv

citations

Self-Correcting Self-Consuming Loops for Generative Model Training

ICML 2024arXiv

citations

Composable Augmentation Encoding for Video Representation Learning

ICCV 2021arXiv

citations

Unsupervised Learning of Shape Programs with Repeatable Implicit Parts

NEURIPS 2022

citations

Yonglong Tian

papers (17)

Supervised Contrastive Learning

Contrastive Multiview Coding

What Makes for Good Views for Contrastive Learning?

Rethinking Few-shot Image Classification: A Good Embedding is All You Need?

Improving CLIP Training with Language Rewrites

StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners

Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens

Divide and Contrast: Self-Supervised Learning From Uncurated Data

Scaling Laws of Synthetic Images for Model Training ... for Now

Restart Sampling for Improving Generative Processes

Learning Vision from Models Rivals Learning Vision from Data

Co-Advise: Cross Inductive Bias Distillation

Vision-Language Models Do Not Understand Negation

Denoising Vision Transformers

Self-Correcting Self-Consuming Loops for Generative Model Training

Composable Augmentation Encoding for Video Representation Learning

Unsupervised Learning of Shape Programs with Repeatable Implicit Parts

papers (17)

Supervised Contrastive Learning

Contrastive Multiview Coding

What Makes for Good Views for Contrastive Learning?

Rethinking Few-shot Image Classification: A Good Embedding is All You Need?

Improving CLIP Training with Language Rewrites

StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners

Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens

Divide and Contrast: Self-Supervised Learning From Uncurated Data

Scaling Laws of Synthetic Images for Model Training ... for Now

Restart Sampling for Improving Generative Processes

Learning Vision from Models Rivals Learning Vision from Data

Co-Advise: Cross Inductive Bias Distillation

Vision-Language Models Do Not Understand Negation

Denoising Vision Transformers

Self-Correcting Self-Consuming Loops for Generative Model Training

Composable Augmentation Encoding for Video Representation Learning

Unsupervised Learning of Shape Programs with Repeatable Implicit Parts